MedicalBenchmark
OpenAI: GPT-4 Turbo provider

GPT-4 Turbo

147

#147 of 319 models in the general ranking

Cumulative performance across 3 MIR exams

Net score

511.00 pts

Accuracy

88.7%

Correct / Incorrect

532 / 63

Total Cost

$12.45

Overall Performance

(vs. average)
Accuracy

88.7%

avg: 80.6%

Net score

511.00 pts

avg: 453.30 pts

Correct

532

avg: 483

Incorrect

63

avg: 90

Total Cost

$12.45

avg: $9.58

Average response time

11.3s

avg: 17.9s

Output Tokens

308K

avg: 1.3M

Reasoning Tokens

0

avg: 898K

Average confidence

98.4%

avg: 95.4%

Breakdown by Exam

MIR 2024
122
Correct
185
Incorrect
15
Accuracy
92.5%
Net score
180.00
MIR 2025
165
Correct
169
Incorrect
29
Accuracy
84.5%
Net score
159.33
MIR 2026
156
Correct
178
Incorrect
19
Accuracy
89.0%
Net score
171.66